FarExStance: Explainable Stance Detection for Farsi
Majid Zarharan, Maryam Hashemi, Malika Behroozrazegh, Sauleh Eetemadi,, Mohammad Taher Pilehvar, Jennifer Foster

TL;DR
This paper presents FarExStance, a new dataset for explainable stance detection in Farsi, and evaluates various models including fine-tuned RoBERTa and large language models on their ability to detect stance and generate explanations.
Contribution
Introduction of FarExStance, a novel dataset for Farsi explainable stance detection, and comprehensive evaluation of multiple models including fine-tuned and large language models.
Findings
Fine-tuned RoBERTa achieved the highest stance detection accuracy.
Few-shot Claude-3.5-Sonnet provided the best explanations according to human evaluation.
GPT-4o generated the most coherent explanations in automatic metrics.
Abstract
We introduce FarExStance, a new dataset for explainable stance detection in Farsi. Each instance in this dataset contains a claim, the stance of an article or social media post towards that claim, and an extractive explanation which provides evidence for the stance label. We compare the performance of a fine-tuned multilingual RoBERTa model to several large language models in zero-shot, few-shot, and parameter-efficient fine-tuned settings on our new dataset. On stance detection, the most accurate models are the fine-tuned RoBERTa model, the LLM Aya-23-8B which has been fine-tuned using parameter-efficient fine-tuning, and few-shot Claude-3.5-Sonnet. Regarding the quality of the explanations, our automatic evaluation metrics indicate that few-shot GPT-4o generates the most coherent explanations, while our human evaluation reveals that the best Overall Explanation Score (OES) belongs to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Advanced Text Analysis Techniques
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Linear Layer · Dropout · Multi-Head Attention · Residual Connection · Adam · Layer Normalization · Weight Decay · Softmax
